mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
94 lines
3.2 KiB
Python
94 lines
3.2 KiB
Python
#!/usr/bin/env python
|
|
# vim:fileencoding=utf-8
|
|
'''
|
|
rt.com
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe, classes
|
|
|
|
|
|
class RT_eng(BasicNewsRecipe):
|
|
title = 'Russia Today'
|
|
__author__ = 'unkn0wn'
|
|
description = '''
|
|
RT creates news with an edge for viewers who want to Question More. RT covers stories overlooked by the mainstream
|
|
media, provides alternative perspectives on current affairs, and acquaints international audiences with a Russian
|
|
viewpoint on major global events.
|
|
'''
|
|
publisher = 'Autonomous Nonprofit Organization "TV-Novosti"'
|
|
category = 'news, politics, economy, finances, Russia, world'
|
|
oldest_article = 1.2
|
|
no_stylesheets = True
|
|
encoding = 'utf-8'
|
|
ignore_duplicate_articles = {'url', 'title'}
|
|
use_embedded_content = False
|
|
remove_empty_feeds = True
|
|
remove_javascript = True
|
|
language = 'en'
|
|
remove_attributes = ['height', 'width', 'style']
|
|
publication_type = 'newsportal'
|
|
|
|
recipe_specific_options = {
|
|
'days': {
|
|
'short': 'Oldest article to download from this news source. In days ',
|
|
'long': 'For example, 0.5, gives you articles from the past 12 hours',
|
|
'default': str(oldest_article)
|
|
}
|
|
}
|
|
|
|
def __init__(self, *args, **kwargs):
|
|
BasicNewsRecipe.__init__(self, *args, **kwargs)
|
|
d = self.recipe_specific_options.get('days')
|
|
if d and isinstance(d, str):
|
|
self.oldest_article = float(d)
|
|
|
|
extra_css = '''
|
|
img {display:block; margin:0 auto;}
|
|
em { color:#202020; }
|
|
.date { font-size:small; color:#404040; }
|
|
.article__summary { font-style:italic; color:#202020; }
|
|
.media__footer { font-size:small; text-align:center; }
|
|
'''
|
|
|
|
conversion_options = {
|
|
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
|
|
}
|
|
|
|
keep_only_tags = [
|
|
dict(name='div', attrs={'class':'article'})
|
|
]
|
|
|
|
remove_tags = [
|
|
dict(name=['meta', 'link', 'svg', 'button', 'style', 'iframe', 'noscript']),
|
|
classes(
|
|
'update_date_visible breadcrumbs read-more Read-more-text-only article__share '
|
|
'article__social-wrapper article__share_bottom'
|
|
)
|
|
]
|
|
|
|
feeds = [
|
|
('Russia', 'https://www.rt.com/rss/russia/'),
|
|
('India', 'https://www.rt.com/rss/india/'),
|
|
('Africa', 'https://www.rt.com/rss/africa/'),
|
|
('World News', 'https://www.rt.com/rss/news/'),
|
|
('Business', 'https://www.rt.com/rss/business/'),
|
|
('Opinion', 'https://www.rt.com/rss/op-ed/'),
|
|
('Culture', 'https://www.rt.com/rss/pop-culture/'),
|
|
('Others', 'https://www.rt.com/rss/')
|
|
]
|
|
|
|
def get_article_url(self, article):
|
|
url = BasicNewsRecipe.get_article_url(self, article)
|
|
return url.split('?')[0]
|
|
|
|
def preprocess_html(self, soup):
|
|
for img in soup.findAll('img'):
|
|
srcset = img.find_previous_sibling('source', attrs={'data-srcset':True})
|
|
if srcset:
|
|
for x in srcset['data-srcset'].split(','):
|
|
if '/l/' in x.split()[0].strip():
|
|
img['src'] = x.split()[0].strip()
|
|
for src in soup.findAll('source'):
|
|
src.decompose()
|
|
return soup
|